Hudson & Thames has provided the following skillset challenge as part of our April 2022 intake for a junior data scientist or machine learning engineer.
The following assignment is an opportunity for you to highlight your skillset and show us what you are made of! It tests your ability to implement research, and to do it in style!
Read the following paper: Enhancing a Pairs Trading strategy with the application of Machine Learning.
Note: The following textbook provides a deeper explanation of the technique.
In a Jupyter Notebook (python):
- Create a private repo on Github for your submission. Use your full name as the repo name.
- Download and save your universe of stocks (use 200-300 shares) (Can use Yahoo finance to get shares data. Checkout the yfinance package.)(Else you can use Polygon)
- Implement Section III: Proposed Pairs Selection Framework (A and B, Section C if you really want to impress)
- Create a set of functions/class for the end-user to make use of.
- Make sure to add docstrings and follow PEP8 code style checks. Have plenty of inline comments, good variable names and don't over complicate things unnecessarily. It should be easy for the user to make use of.
- Showcase your new Pairs Selection Framework in a Jupyter Notebook and show us some visualizations of the clusters and pairs (Think Plotly and Dash).
- Add an introduction, body, and conclusion showcasing your new implementation. (Use the correct style headers)
- Invite us ([email protected]) to your private repo so that we can evaluate your work.
- Bonus points if you add unit tests (in a separate .py file).
- Friday the 29th of April 2022.
- We assign additional points to those that submit high quality work early on.
- Don't leave it until last moment.
- Your code for the implementation should be contained in a .py file that you import into your notebook. Please don't have large chunks of code in your notebook.
- Save your data with your repo so that we can evaluate it.
- Keep in mind that if you don't have enough rows of data to support the number of assets in your universe, the PCA will not be able to extract meaning full factors.
- Candidates that have analysed previous code reviews of our skill set challenges, perform a lot better.
- Company Name: Hudson and Thames Quantitative Research
- Company Brief: Our core focus is the implementation of state-of-the-art algorithms, to solve problems in buy side asset management.
- Company Website: https://hudsonthames.org/
- Locked Achievement: Junior Data Scientist / Machine Learning Engineer.
- Education: Familiarity with machine learning, statistics, and applied maths. We care a lot more about what you can do rather than your exact qualifications.